Computational Radiomics System to Decode the Radiographic Phenotype

Radiomics aims to quantify phenotypic characteristics on medical imaging through the use of automated algorithms. Radiomic artificial intelligence (AI) technology, either based on engineered hard-coded algorithms or deep learning methods, can be used to develop noninvasive imaging-based biomarkers. However, lack of standardized algorithm definitions and image processing severely hampers reproducibility and comparability of results. To address this issue, we developed PyRadiomics, a flexible open-source platform capable of extracting a large panel of engineered features from medical images. PyRadiomics is implemented in Python and can be used standalone or using 3D Slicer. Here, we discuss the workflow and architecture of PyRadiomics and demonstrate its application in characterizing lung lesions. Source code, documentation, and examples are publicly available at www.radiomics.io With this platform, we aim to establish a reference standard for radiomic analyses, provide a tested and maintained resource, and to grow the community of radiomic developers addressing critical needs in cancer research. Cancer Res; 77(21); e104-7. ©2017 AACR.

Radiomics: extracting more information from medical images using advanced feature analysis

Solid cancers are spatially and temporally heterogeneous. This limits the use of invasive biopsy based molecular assays but gives huge potential for medical imaging, which has the ability to capture intra-tumoural heterogeneity in a non-invasive way. During the past decades, medical imaging innovations with new hardware, new imaging agents and standardised protocols, allows the field to move towards quantitative imaging. Therefore, also the development of automated and reproducible analysis methodologies to extract more information from image-based features is a requirement. Radiomics--the high-throughput extraction of large amounts of image features from radiographic images--addresses this problem and is one of the approaches that hold great promises but need further validation in multi-centric settings and in the laboratory.

Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

Human cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.

An individual tumour is often heterogeneous and its various features can be visualised noninvasively using medical imaging. Here, the authors analyse large computed tomography data sets using radiomic algorithms to identify heterogeneity, and find that some of these tumour features have prognostic value across cancer types.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Artificial intelligence in radiology

Artificial intelligence (AI) algorithms, particularly deep learning, have demonstrated remarkable progress in image-recognition tasks. Methods ranging from convolutional neural networks to variational autoencoders have found myriad applications in the medical image analysis field, propelling it forward at a rapid pace. Historically, in radiology practice, trained physicians visually assessed medical images for the detection, characterization and monitoring of diseases. AI methods excel at automatically recognizing complex patterns in imaging data and providing quantitative, rather than qualitative, assessments of radiographic characteristics. In this Opinion article, we establish a general understanding of AI methods, particularly those pertaining to image-based tasks. We explore how these methods could impact multiple facets of radiology, with a general focus on applications in oncology, and demonstrate ways in which these methods are advancing the field. Finally, we discuss the challenges facing clinical implementation and provide our perspective on how the domain could be advanced.

Phylogenetic ctDNA analysis depicts early-stage lung cancer evolution

The early detection of relapse following primary surgery for non-small-cell lung cancer and the characterization of emerging subclones, which seed metastatic sites, might offer new therapeutic approaches for limiting tumour recurrence. The ability to track the evolutionary dynamics of early-stage lung cancer non-invasively in circulating tumour DNA (ctDNA) has not yet been demonstrated. Here we use a tumour-specific phylogenetic approach to profile the ctDNA of the first 100 TRACERx (Tracking Non-Small-Cell Lung Cancer Evolution Through Therapy (Rx)) study participants, including one patient who was also recruited to the PEACE (Posthumous Evaluation of Advanced Cancer Environment) post-mortem study. We identify independent predictors of ctDNA release and analyse the tumour-volume detection limit. Through blinded profiling of postoperative plasma, we observe evidence of adjuvant chemotherapy resistance and identify patients who are very likely to experience recurrence of their lung cancer. Finally, we show that phylogenetic ctDNA profiling tracks the subclonal nature of lung cancer relapse and metastasis, providing a new approach for ctDNA-driven therapeutic studies.

Applications and limitations of radiomics

Radiomics is an emerging field in quantitative imaging that uses advanced imaging features to objectively and quantitatively describe tumour phenotypes. Radiomic features have recently drawn considerable interest due to its potential predictive power for treatment outcomes and cancer genetics, which may have important applications in personalized medicine. In this technical review, we describe applications and challenges of the radiomic field. We will review radiomic application areas and technical issues, as well as proper practices for the designs of radiomic studies.

Artificial intelligence in cancer imaging: Clinical challenges and applications

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

Imaging biomarker roadmap for cancer studies

Imaging biomarkers (IBs) are integral to the routine management of patients with cancer. IBs used daily in oncology include clinical TNM stage, objective response and left ventricular ejection fraction. Other CT, MRI, PET and ultrasonography biomarkers are used extensively in cancer research and drug development. New IBs need to be established either as useful tools for testing research hypotheses in clinical trials and research studies, or as clinical decision-making tools for use in healthcare, by crossing 'translational gaps' through validation and qualification. Important differences exist between IBs and biospecimen-derived biomarkers and, therefore, the development of IBs requires a tailored 'roadmap'. Recognizing this need, Cancer Research UK (CRUK) and the European Organisation for Research and Treatment of Cancer (EORTC) assembled experts to review, debate and summarize the challenges of IB validation and qualification. This consensus group has produced 14 key recommendations for accelerating the clinical translation of IBs, which highlight the role of parallel (rather than sequential) tracks of technical (assay) validation, biological/clinical validation and assessment of cost-effectiveness; the need for IB standardization and accreditation systems; the need to continually revisit IB precision; an alternative framework for biological/clinical validation of IBs; and the essential requirements for multicentre studies to qualify IBs for clinical use.

Machine Learning methods for Quantitative Radiomic Biomarkers

Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.

CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma

BACKGROUND AND PURPOSE

Radiomics provides opportunities to quantify the tumor phenotype non-invasively by applying a large number of quantitative imaging features. This study evaluates computed-tomography (CT) radiomic features for their capability to predict distant metastasis (DM) for lung adenocarcinoma patients.

MATERIAL AND METHODS

We included two datasets: 98 patients for discovery and 84 for validation. The phenotype of the primary tumor was quantified on pre-treatment CT-scans using 635 radiomic features. Univariate and multivariate analysis was performed to evaluate radiomics performance using the concordance index (CI).

RESULTS

Thirty-five radiomic features were found to be prognostic (CI>0.60, FDR<5%) for DM and twelve for survival. It is noteworthy that tumor volume was only moderately prognostic for DM (CI=0.55, p-value=2.77×10(-5)) in the discovery cohort. A radiomic-signature had strong power for predicting DM in the independent validation dataset (CI=0.61, p-value=1.79×10(-17)). Adding this radiomic-signature to a clinical model resulted in a significant improvement of predicting DM in the validation dataset (p-value=1.56×10(-11)).

CONCLUSIONS

Although only basic metrics are routinely quantified, this study shows that radiomic features capturing detailed information of the tumor phenotype can be used as a prognostic biomarker for clinically-relevant factors such as DM. Moreover, the radiomic-signature provided additional information to clinical data.

The Potential of Radiomic-Based Phenotyping in Precision Medicine: A Review

Importance

Advances in genomics have led to the recognition that tumors are populated by distinct genotypic subgroups that drive tumor development and progression. The spatial and temporal heterogeneity of solid tumors has been a critical barrier to the development of precision medicine approaches because the standard approach to tumor sampling, often invasive needle biopsy, is unable to fully capture the spatial state of the tumor. Image-based phenotyping, which represents quantification of the tumor phenotype through medical imaging, is a promising development for precision medicine.

Observations

Medical imaging can provide a comprehensive macroscopic picture of the tumor phenotype and its environment that is ideally suited to quantifying the development of the tumor phenotype before, during, and after treatment. As a noninvasive technique, medical imaging can be performed at low risk and inconvenience to the patient. The semantic features approach to tumor phenotyping, accomplished by visual assessment of radiologists, is compared with a computational radiomic approach that relies on automated processing of imaging assays. Together, these approaches capture important information for diagnostic, prognostic, and predictive purposes.

Conclusions and Relevance

Although imaging technology is already embedded in clinical practice for diagnosis, staging, treatment planning, and response assessment, the transition of these computational methods to the clinic has been surprisingly slow. This review outlines the promise of these novel technologies for precision medicine and the obstacles to clinical application.

Robust Radiomics feature quantification using semiautomatic volumetric segmentation

Due to advances in the acquisition and analysis of medical imaging, it is currently possible to quantify the tumor phenotype. The emerging field of Radiomics addresses this issue by converting medical images into minable data by extracting a large number of quantitative imaging features. One of the main challenges of Radiomics is tumor segmentation. Where manual delineation is time consuming and prone to inter-observer variability, it has been shown that semi-automated approaches are fast and reduce inter-observer variability. In this study, a semiautomatic region growing volumetric segmentation algorithm, implemented in the free and publicly available 3D-Slicer platform, was investigated in terms of its robustness for quantitative imaging feature extraction. Fifty-six 3D-radiomic features, quantifying phenotypic differences based on tumor intensity, shape and texture, were extracted from the computed tomography images of twenty lung cancer patients. These radiomic features were derived from the 3D-tumor volumes defined by three independent observers twice using 3D-Slicer, and compared to manual slice-by-slice delineations of five independent physicians in terms of intra-class correlation coefficient (ICC) and feature range. Radiomic features extracted from 3D-Slicer segmentations had significantly higher reproducibility (ICC = 0.85±0.15, p = 0.0009) compared to the features extracted from the manual segmentations (ICC = 0.77±0.17). Furthermore, we found that features extracted from 3D-Slicer segmentations were more robust, as the range was significantly smaller across observers (p = 3.819e-07), and overlapping with the feature ranges extracted from manual contouring (boundary lower: p = 0.007, higher: p = 5.863e-06). Our results show that 3D-Slicer segmented tumor volumes provide a better alternative to the manual delineation for feature quantification, as they yield more reproducible imaging descriptors. Therefore, 3D-Slicer can be employed for quantitative image feature extraction and image data mining research in large patient cohorts.

Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers

INTRODUCTION

Immunotherapy is regarded as one of the major breakthroughs in cancer treatment. Despite its success, only a subset of patients responds-urging the quest for predictive biomarkers. We hypothesize that artificial intelligence (AI) algorithms can automatically quantify radiographic characteristics that are related to and may therefore act as noninvasive radiomic biomarkers for immunotherapy response.

PATIENTS AND METHODS

In this study, we analyzed 1055 primary and metastatic lesions from 203 patients with advanced melanoma and non-small-cell lung cancer (NSCLC) undergoing anti-PD1 therapy. We carried out an AI-based characterization of each lesion on the pretreatment contrast-enhanced CT imaging data to develop and validate a noninvasive machine learning biomarker capable of distinguishing between immunotherapy responding and nonresponding. To define the biological basis of the radiographic biomarker, we carried out gene set enrichment analysis in an independent dataset of 262 NSCLC patients.

RESULTS

The biomarker reached significant performance on NSCLC lesions (up to 0.83 AUC, P < 0.001) and borderline significant for melanoma lymph nodes (0.64 AUC, P = 0.05). Combining these lesion-wide predictions on a patient level, immunotherapy response could be predicted with an AUC of up to 0.76 for both cancer types (P < 0.001), resulting in a 1-year survival difference of 24% (P = 0.02). We found highly significant associations with pathways involved in mitosis, indicating a relationship between increased proliferative potential and preferential response to immunotherapy.

CONCLUSIONS

These results indicate that radiographic characteristics of lesions on standard-of-care imaging may function as noninvasive biomarkers for response to immunotherapy, and may show utility for improved patient stratification in both neoadjuvant and palliative settings.

Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study

BACKGROUND

Non-small-cell lung cancer (NSCLC) patients often demonstrate varying clinical courses and outcomes, even within the same tumor stage. This study explores deep learning applications in medical imaging allowing for the automated quantification of radiographic characteristics and potentially improving patient stratification.

METHODS AND FINDINGS

We performed an integrative analysis on 7 independent datasets across 5 institutions totaling 1,194 NSCLC patients (age median = 68.3 years [range 32.5-93.3], survival median = 1.7 years [range 0.0-11.7]). Using external validation in computed tomography (CT) data, we identified prognostic signatures using a 3D convolutional neural network (CNN) for patients treated with radiotherapy (n = 771, age median = 68.0 years [range 32.5-93.3], survival median = 1.3 years [range 0.0-11.7]). We then employed a transfer learning approach to achieve the same for surgery patients (n = 391, age median = 69.1 years [range 37.2-88.0], survival median = 3.1 years [range 0.0-8.8]). We found that the CNN predictions were significantly associated with 2-year overall survival from the start of respective treatment for radiotherapy (area under the receiver operating characteristic curve [AUC] = 0.70 [95% CI 0.63-0.78], p < 0.001) and surgery (AUC = 0.71 [95% CI 0.60-0.82], p < 0.001) patients. The CNN was also able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy (p < 0.001) and surgery (p = 0.03) datasets. Additionally, the CNN was found to significantly outperform random forest models built on clinical parameters-including age, sex, and tumor node metastasis stage-as well as demonstrate high robustness against test-retest (intraclass correlation coefficient = 0.91) and inter-reader (Spearman's rank-order correlation = 0.88) variations. To gain a better understanding of the characteristics captured by the CNN, we identified regions with the most contribution towards predictions and highlighted the importance of tumor-surrounding tissue in patient stratification. We also present preliminary findings on the biological basis of the captured phenotypes as being linked to cell cycle and transcriptional processes. Limitations include the retrospective nature of this study as well as the opaque black box nature of deep learning networks.

CONCLUSIONS

Our results provide evidence that deep learning networks may be used for mortality risk stratification based on standard-of-care CT images from NSCLC patients. This evidence motivates future research into better deciphering the clinical and biological basis of deep learning networks as well as validation in prospective data.

Stability of FDG-PET Radiomics features: an integrated analysis of test-retest and inter-observer variability

PURPOSE

Besides basic measurements as maximum standardized uptake value (SUV)max or SUVmean derived from 18F-FDG positron emission tomography (PET) scans, more advanced quantitative imaging features (i.e. "Radiomics" features) are increasingly investigated for treatment monitoring, outcome prediction, or as potential biomarkers. With these prospected applications of Radiomics features, it is a requisite that they provide robust and reliable measurements. The aim of our study was therefore to perform an integrated stability analysis of a large number of PET-derived features in non-small cell lung carcinoma (NSCLC), based on both a test-retest and an inter-observer setup.

METHODS

Eleven NSCLC patients were included in the test-retest cohort. Patients underwent repeated PET imaging within a one day interval, before any treatment was delivered. Lesions were delineated by applying a threshold of 50% of the maximum uptake value within the tumor. Twenty-three NSCLC patients were included in the inter-observer cohort. Patients underwent a diagnostic whole body PET-computed tomography (CT). Lesions were manually delineated based on fused PET-CT, using a standardized clinical delineation protocol. Delineation was performed independently by five observers, blinded to each other. Fifteen first order statistics, 39 descriptors of intensity volume histograms, eight geometric features and 44 textural features were extracted. For every feature, test-retest and inter-observer stability was assessed with the intra-class correlation coefficient (ICC) and the coefficient of variability, normalized to mean and range. Similarity between test-retest and inter-observer stability rankings of features was assessed with Spearman's rank correlation coefficient.

RESULTS

Results showed that the majority of assessed features had both a high test-retest (71%) and inter-observer (91%) stability in terms of their ICC. Overall, features more stable in repeated PET imaging were also found to be more robust against inter-observer variability.

CONCLUSION

Results suggest that further research of quantitative imaging features is warranted with respect to more advanced applications of PET imaging as being used for treatment monitoring, outcome prediction or imaging biomarkers.

Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer

Radiomics provides a comprehensive quantification of tumor phenotypes by extracting and mining large number of quantitative image features. To reduce the redundancy and compare the prognostic characteristics of radiomic features across cancer types, we investigated cancer-specific radiomic feature clusters in four independent Lung and Head & Neck (H∓N) cancer cohorts (in total 878 patients). Radiomic features were extracted from the pre-treatment computed tomography (CT) images. Consensus clustering resulted in eleven and thirteen stable radiomic feature clusters for Lung and H & N cancer, respectively. These clusters were validated in independent external validation cohorts using rand statistic (Lung RS = 0.92, p < 0.001, H & N RS = 0.92, p < 0.001). Our analysis indicated both common as well as cancer-specific clustering and clinical associations of radiomic features. Strongest associations with clinical parameters: Prognosis Lung CI = 0.60 ± 0.01, Prognosis H & N CI = 0.68 ± 0.01; Lung histology AUC = 0.56 ± 0.03, Lung stage AUC = 0.61 ± 0.01, H & N HPV AUC = 0.58 ± 0.03, H & N stage AUC = 0.77 ± 0.02. Full utilization of these cancer-specific characteristics of image features may further improve radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor phenotypic characteristics in clinical practice.

The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis

FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) R_D, dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) R_B, maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, R_B was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging

PURPOSE

Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non-small cell lung cancer (NSCLC).Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans).

RESULTS

Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17-17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016).

CONCLUSIONS

We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer

Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered CT image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n = 353) and verified them in an independent validation cohort (n = 352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfully discriminated between EGFR⁺ and EGFR^- cases (AUC = 0.69). Combining this signature with a clinical model of EGFR status (AUC = 0.70) significantly improved prediction accuracy (AUC = 0.75). The highest performing signature was capable of distinguishing between EGFR⁺ and KRAS⁺ tumors (AUC = 0.80) and, when combined with a clinical model (AUC = 0.81), substantially improved its performance (AUC = 0.86). A KRAS⁺/KRAS^- radiomic signature also showed significant albeit lower performance (AUC = 0.63) and did not improve the accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied noninvasively, repeatedly, and at low cost. Cancer Res; 77(14); 3922-30. ©2017 AACR.

Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer

INTRODUCTION

"Radiomics" extracts and mines a large number of medical imaging features in a non-invasive and cost-effective way. The underlying assumption of radiomics is that these imaging features quantify phenotypic characteristics of an entire tumor. In order to enhance applicability of radiomics in clinical oncology, highly accurate and reliable machine-learning approaches are required. In this radiomic study, 13 feature selection methods and 11 machine-learning classification methods were evaluated in terms of their performance and stability for predicting overall survival in head and neck cancer patients.

METHODS

Two independent head and neck cancer cohorts were investigated. Training cohort HN1 consisted of 101 head and neck cancer patients. Cohort HN2 (n = 95) was used for validation. A total of 440 radiomic features were extracted from the segmented tumor regions in CT images. Feature selection and classification methods were compared using an unbiased evaluation framework.

RESULTS

We observed that the three feature selection methods minimum redundancy maximum relevance (AUC = 0.69, Stability = 0.66), mutual information feature selection (AUC = 0.66, Stability = 0.69), and conditional infomax feature extraction (AUC = 0.68, Stability = 0.7) had high prognostic performance and stability. The three classifiers BY (AUC = 0.67, RSD = 11.28), RF (AUC = 0.61, RSD = 7.36), and NN (AUC = 0.62, RSD = 10.52) also showed high prognostic performance and stability. Analysis investigating performance variability indicated that the choice of classification method is the major factor driving the performance variation (29.02% of total variance).

CONCLUSION

Our study identified prognostic and reliable machine-learning methods for the prediction of overall survival of head and neck cancer patients. Identification of optimal machine-learning methods for radiomics-based prognostic analyses could broaden the scope of radiomics in precision oncology and cancer care.

Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology

Background

Radiomics can quantify tumor phenotypic characteristics non-invasively by applying feature algorithms to medical imaging data. In this study of lung cancer patients, we investigated the association between radiomic features and the tumor histologic subtypes (adenocarcinoma and squamous cell carcinoma). Furthermore, in order to predict histologic subtypes, we employed machine-learning methods and independently evaluated their prediction performance.

Methods

Two independent radiomic cohorts with a combined size of 350 patients were included in our analysis. A total of 440 radiomic features were extracted from the segmented tumor volumes of pretreatment CT images. These radiomic features quantify tumor phenotypic characteristics on medical images using tumor shape and size, intensity statistics, and texture. Univariate analysis was performed to assess each feature’s association with the histological subtypes. In our multivariate analysis, we investigated 24 feature selection methods and 3 classification methods for histology prediction. Multivariate models were trained on the training cohort and their performance was evaluated on the independent validation cohort using the area under ROC curve (AUC). Histology was determined from surgical specimen.

Results

In our univariate analysis, we observed that fifty-three radiomic features were significantly associated with tumor histology. In multivariate analysis, feature selection methods ReliefF and its variants showed higher prediction accuracy as compared to other methods. We found that Naive Baye’s classifier outperforms other classifiers and achieved the highest AUC (0.72; p-value = 2.3 × 10⁻⁷) with five features: Stats_min, Wavelet_HLL_rlgl_lowGrayLevelRunEmphasis, Wavelet_HHL_stats_median, Wavelet_HLL_stats_skewness, and Wavelet_HLH_glcm_clusShade.

Conclusion

Histological subtypes can influence the choice of a treatment/therapy for lung cancer patients. We observed that radiomic features show significant association with the lung tumor histology. Moreover, radiomics-based multivariate classifiers were independently validated for the prediction of histological subtypes. Despite achieving lower than optimal prediction accuracy (AUC 0.72), our analysis highlights the impressive potential of non-invasive and cost-effective radiomics for precision medicine. Further research in this direction could lead us to optimal performance and therefore to clinical applicability, which could enhance the efficiency and efficacy of cancer care.

Radiomic phenotype features predict pathological response in non-small cell lung cancer

BACKGROUND AND PURPOSE

Radiomics can quantify tumor phenotype characteristics non-invasively by applying advanced imaging feature algorithms. In this study we assessed if pre-treatment radiomics data are able to predict pathological response after neoadjuvant chemoradiation in patients with locally advanced non-small cell lung cancer (NSCLC).

MATERIALS AND METHODS

127 NSCLC patients were included in this study. Fifteen radiomic features selected based on stability and variance were evaluated for its power to predict pathological response. Predictive power was evaluated using area under the curve (AUC). Conventional imaging features (tumor volume and diameter) were used for comparison.

RESULTS

Seven features were predictive for pathologic gross residual disease (AUC>0.6, p-value<0.05), and one for pathologic complete response (AUC=0.63, p-value=0.01). No conventional imaging features were predictive (range AUC=0.51-0.59, p-value>0.05). Tumors that did not respond well to neoadjuvant chemoradiation were more likely to present a rounder shape (spherical disproportionality, AUC=0.63, p-value=0.009) and heterogeneous texture (LoG 5mm 3D - GLCM entropy, AUC=0.61, p-value=0.03).

CONCLUSION

We identified predictive radiomic features for pathological response, although no conventional features were significantly predictive. This study demonstrates that radiomics can provide valuable clinical information, and performed better than conventional imaging features.

Vulnerabilities of radiomic signature development: The need for safeguards

PURPOSE

Refinement of radiomic results and methodologies is required to ensure progression of the field. In this work, we establish a set of safeguards designed to improve and support current radiomic methodologies through detailed analysis of a radiomic signature.

METHODS

A radiomic model (MW2018) was fitted and externally validated using features extracted from previously reported lung and head and neck (H&N) cancer datasets using gross-tumour-volume contours, as well as from images with randomly permuted voxel index values; i.e. images without meaningful texture. To determine MW2018's added benefit, the prognostic accuracy of tumour volume alone was calculated as a baseline.

RESULTS

MW2018 had an external validation concordance index (c-index) of 0.64. However, a similar performance was achieved using features extracted from images with randomized signal intensities (c-index = 0.64 and 0.60 for H&N and lung, respectively). Tumour volume had a c-index = 0.64 and correlated strongly with three of the four model features. It was determined that the signature was a surrogate for tumour volume and that intensity and texture values were not pertinent for prognostication.

CONCLUSION

Our experiments reveal vulnerabilities in radiomic signature development processes and suggest safeguards that can be used to refine methodologies, and ensure productive radiomic development using objective and independent features.

Cardiac Radiation Dose, Cardiac Disease, and Mortality in Patients With Lung Cancer

BACKGROUND

Radiotherapy-associated cardiac toxicity studies in patients with locally advanced non-small cell lung cancer (NSCLC) have been limited by small sample size and nonvalidated cardiac endpoints.

OBJECTIVES

The purpose of this analysis was to ascertain whether cardiac radiation dose is a predictor of major adverse cardiac events (MACE) and all-cause mortality (ACM).

METHODS

This retrospective analysis included 748 consecutive locally advanced NSCLC patients treated with thoracic radiotherapy. Fine and Gray and Cox regressions were used to identify predictors for MACE and ACM, adjusting for lung cancer and cardiovascular prognostic factors, including pre-existing coronary heart disease (CHD).

RESULTS

After a median follow-up of 20.4 months, 77 patients developed ≥1 MACE (2-year cumulative incidence, 5.8%; 95% confidence interval [CI]: 4.3% to 7.7%), and 533 died. Mean radiation dose delivered to the heart (mean heart dose) was associated with a significantly increased risk of MACE (adjusted hazard ratio [HR]: 1.05/Gy; 95% CI: 1.02 to 1.08/Gy; p < 0.001) and ACM (adjusted HR: 1.02/Gy; 95% CI: 1.00 to 1.03/Gy; p = 0.007). Mean heart dose (≥10 Gy vs. <10 Gy) was associated with a significantly increased risk of ACM in CHD-negative patients (178 vs. 118 deaths; HR: 1.34; 95% CI: 1.06 to 1.69; p = 0.014) with 2-year estimates of 52.2% (95% CI: 46.1% to 58.5%) versus 40.0% (95% CI: 33.5% to 47.4%); but not among CHD-positive patients (112 vs. 82 deaths; HR: 0.94; 95% CI: 0.70 to 1.25; p = 0.66) with 2-year estimates of 54.6% (95% CI: 46.8% to 62.7%) versus 50.8% (95% CI: 41.5% to 60.9%), respectively (p for interaction = 0.028).

CONCLUSIONS

Despite the competing risk of cancer-specific death in locally advanced NSCLC patients, cardiac radiation dose exposure is a modifiable cardiac risk factor for MACE and ACM, supporting the need for early recognition and treatment of cardiovascular events and more stringent avoidance of high cardiac radiotherapy dose.